Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Agents Are Not Enough

arxiv.org

Post reply on HN
Print view View original

141–150 of 165 posts

Re: Agents Are Not Enough

#141

Post by sgt101 »

HarHarVeryFunny wrote: post #92
georgestrakhov wrote: post #28

IMHO, the word agent is quickly becoming meaningless. The amount of agency that sits with the program vs. the user is something that changes gradually. So we should think about these things in terms of how much agency are we willing to give away in each case and for what gain[1]. Then the ecosystem question that the paper is trying to solve will actually solve itself, because it is already the case today that in many…

An agent, or something that has agency, is just something that takes some action, which could be anything from a thermostat regulating the temperature all the way up to an autonomous entity such as an animal going about it's business. Hugging Face have their own definitions of a few different types of agent/agentic system here: https://huggingface.co/docs/smolagents/en/conceptual_guides/... As related to LLMs, it see…

Hi - have a look at this book if you are interested [1] (Mike Wooldridge, Multi-Agent Systems)

[1] https://amzn.eu/d/6a1KgnL

Here are Mike's credentials :https://www.cs.ox.ac.uk/people/michael.wooldridge/

Re: Agents Are Not Enough

#142

Post by sgt101 »

TaurenHunter wrote: post #9

"More Agents is all you need" https://arxiv.org/abs/2402.05120 I could not find a "Agents considered harmful" related to AI, but there is this one: "AgentHarm: A benchmark for measuring harmfulness of LLM agents" https://arxiv.org/pdf/2410.09024 This "Agents considered harmful" is not AI-related: https://www.scribd.com/document/361564026/Math-works-09

Hi - have a look at this book if you are interested [1] (Mike Wooldridge, Multi-Agent Systems)

[1] https://amzn.eu/d/6a1KgnL

Here are Mike's credentials :https://www.cs.ox.ac.uk/people/michael.wooldridge/

Re: Agents Are Not Enough

#143

Post by sgt101 »

duxup wrote: post #49
danielmarkbruce wrote: post #42

Why post this paper? It says nothing, it's a waste of people's time to read.

Even just the definition of an Agent (maybe imperfect) made it worthwhile for me.

Hi - have a look at this book if you are interested [1] (Mike Wooldridge, Multi-Agent Systems)

[1] https://amzn.eu/d/6a1KgnL

Here are Mike's credentials :https://www.cs.ox.ac.uk/people/michael.wooldridge/

Re: Agents Are Not Enough

#144

Post by vrighter »

tonetegeatinst wrote: post #59

Somewhat related but here's my take on super intelligence or AGI. I have worked with CNN,GNN and other old school AI methods, but don't have the resources to build a real SOT LLM, but I do use and tinker with LLM's occasionally. If AGI or SI(super intelligence)/is possible, and that is an if...I don't think LLM's are going to be this silver bullet solution Just as we have in the real world of people who are dedicated…

Once I was high and thought of hallucinations as "noise in the output". From that perspective, and the fact that LLMs are probabilistic machines, then halving the noise would probably involve 4x the computation needed. Which seems to track what I observe. Models are getting MUCH larger, but performance is practically at a standstill.

Re: Agents Are Not Enough

#145

Post by vrighter »

skrebbel wrote: post #139
Terr_ wrote: post #93

Earlier quoted context omitted.

> It's just that since the masses found that they can talk to an AI like a human In a way it's worse: Even the "talking to" part is an illusion, and unfortunately a lot of technical people have trouble remembering it too. In truth, the LLM is an idiot-savant which dreams up "fitting" additions to a given document. Some humans have prepared a document which is in the form of a a theater-play or a turn-based chat trans…

> In truth, the LLM is an idiot-savant which dreams up "fitting" additions to a given document. Tbh I'm not too sure that my brain works fundamentally differently. I'm an idiot-savant who responds to stimuli.

Do you know the number of atoms in my coffee cup right now?

If you say "No, I don't" then you're already way ahead of any LLM, even the biggest ones. Remember, I asked about how many are in there right now. The only correct answer is "I don't know", because I haven't even told you whether my mug is full or empty.

Here's copilot's answer:

    how many hydrogen atoms are there in my coffee cup right now
    Copilot said:

    That's an interesting question! The number of hydrogen atoms in your coffee cup depends on the volume of coffee and its composition.

    Let's assume you have a standard coffee cup that holds about 240 milliliters (8 ounces) of coffee. Coffee is mostly water, so we can approximate the number of hydrogen atoms based on the water content.

    Water (H₂O) has 2 hydrogen atoms per molecule. The molar mass of water is approximately 18 grams per mole, and 1 mole of water contains Avogadro's number of molecules, which is about (6.022 \times 10^{23}) molecules.

    1 milliliter of water weighs about 1 gram, so 240 milliliters of water weighs 240 grams. This is approximately ( \frac{240}{18} \approx 13.33 ) moles of water.

    Therefore, the number of water molecules in 240 milliliters of water is: [ 13.33 \times 6.022 \times 10^{23} \approx 8.02 \times 10^{24} \text{ molecules} ]

    Since each water molecule has 2 hydrogen atoms, the total number of hydrogen atoms is: [ 2 \times 8.02 \times 10^{24} \approx 1.60 \times 10^{25} \text{ hydrogen atoms} ]

    So, there are approximately (1.60 \times 10^{25}) hydrogen atoms in a standard coffee cup of 240 milliliters. Keep in mind this is a rough estimate, as the actual number can vary based on the exact composition of your coffee.
If I wanted an explanation of how to approximate it, that's what I would have asked for. You could very probably figure that much out.

Re: Agents Are Not Enough

#146

Post by vrighter »

kgeist wrote: post #16
svieira wrote: post #15

Earlier quoted context omitted.

The bit you are missing is that "known to the system" is not enough, as the consumer I need to _verify the logic_, which means that at some level, I do have to read the DSL (just as I have to read the Java, not, in general, the actual assembly emitted by the JIT). Which means that the DSL is actually the product here (though the LLM may make it easier to learn that DSL and in some cases to write something in it).

1) You don't need to read the DSL in the raw form if you use a language model to convert it to a few paragraphs in natural language. 2) You can test the created workflow on a bunch of test data to verify it works as intended. After a workflow is created, it's deterministic (since we don't use LLMs anymore for decision making), so it will always work the same. Sure we can expose DSL to power users as an option, but is…

NAtural language isn't precise enough to describe exactly what's happening. If you do try to use natural language for that purpose, trying to eliminate ambiguity, you end up with legalese. And people can't read legalese, even though it's technically "plain english"

Re: Agents Are Not Enough

#147

Post by klibertp »

Terr_ wrote: post #91
lugu wrote: post #87

Earlier quoted context omitted.

I am not sure what you mean by LLM when you say they are professional bullshitter. While it was certainly true for model based on transformers just doing inference, recent models have progressed significantly.

> I am not sure what you mean by LLM when you say they are professional bullshitter. Not parent-poster, but an LLM is a tool for extending a document by choosing whatever statistically-seems-right based on other documents, and it does so with no consideration of worldly facts and no modeling of logical prepositions or contradictions. (Which also relates to math problems.) If it has been fed on documents with logic pu…

> The word "bullshit" is appropriate because human bullshitter is someone who picks whatever "seems right" with no particular relation to facts or logical consistency.

Not quite true - this is true for your random bullshitter, but professional bullshitters do, in fact, care for the impression of logical consistency and do have a grip on basic facts (if only so they can handwave them more effectively). As such, LLMs are definitely not yet pros at bullshitting :)

Re: Agents Are Not Enough

#148

Post by vrighter »

deadbabe wrote: post #17
GiorgioG wrote: post #3

Earlier quoted context omitted.

re: LLM as UI: Given that I don't trust LLMs to be deterministic, I wouldn't trust them to make the correct API call every time I tell it to do X.

They are deterministic at 0 temperature

Not really, not in practice. The order of execution is non-deterministic when running on a cluster or a gpu, or more than one core of the CPU and rounding errors propagate differently on each run.

Re: Agents Are Not Enough

#149

Post by 9rx »

trescenzi wrote: post #112
Upvoter33 wrote: post #99

Earlier quoted context omitted.

"If AGI ... is possible" I don't get this line of thinking. AGI already exists - it's in our heads! So then the question is: is what's in our heads magic, or can we build it? If you think it's magic, fine - no point arguing. But if not, we will build it one day.

GI is in our heads. The A is artificial which means built by humans. They are asking the same question you are.

> GI is in our heads. The A is artificial which means built by humans.

Humans aren’t built by humans? Where do humans come from, then?

They say the kids aren’t having sex anymore, but I didn’t realize it was because they aren’t aware of the function.

Re: Agents Are Not Enough

#150

Post by dartos »

widdershins wrote: post #136
Terr_ wrote: post #91

Earlier quoted context omitted.

> I am not sure what you mean by LLM when you say they are professional bullshitter. Not parent-poster, but an LLM is a tool for extending a document by choosing whatever statistically-seems-right based on other documents, and it does so with no consideration of worldly facts and no modeling of logical prepositions or contradictions. (Which also relates to math problems.) If it has been fed on documents with logic pu…

> it does so with no consideration of worldly facts Why don't you consider its training set (usually the entire internet, basically) worldly facts? It's true that the training set can contain contradictory facts, but usually an LLM can recognize these contradictions and provide analysis of the different viewpoints. I don't see how this is much different from what humans can do with documents. The difference is that h…

LLMs are trained with a data which may contain both truthful and false information.

But at inference time it’s not referring to that data at all. Some of the data is aliased and encoded in the model’s weights, but we’re not sure exactly what’s encoded.

It may very well be that vague concepts (like man, woman, animal, unhealthy) are encoded, but not details themselves.

Further, at inference time, there is no kind of “referencing” step. We’ve just seen that they can sometimes repeat text they were trained on, but sometimes they just don’t.

The LLM based systems you’re probably using do some RAG work to insert relevant information in the LLM’s context. This context still is not being referred to per se. An LLM might have a document that says the sky is red, but still insist that it’s blue (or vice versa)

So while the info an LLM may have available is limited by its training data and the RAG system around it, none of that is guaranteed at inference time.

There’s always a significant chance for the LLM to make up bullshit.

Post reply on HN